A PSO-based Neural Network for Multiple-response Optimization

Abstract

An important problem in manufacturing or product and process design is the optimization of several responses simultaneously. Common approaches for multiple response optimization problems often begin with estimating the relationship between responses as outputs and control factors as inputs. Among these methods, response surface methodology (RSM), has attracted more attention in recent years, but in certain cases, the relationship between responses and control factors is far too complex to be efficiently estimated by regression models and the RSM method especially when we want to optimize several responses simultaneously. An alternative approach proposed in this paper is to use an artificial neural network (ANN) to estimate the response functions, Because of the high mean square error (MSE) in the neural network training step we use heuristic algorithms instead of Descent Gradient-based algorithms. In the optimization phase, a particle swarm optimization (PSO) and desirability function are considered to determine the optimal settings for the control factors. Two case studies from the literature are prepared to illustrate the strength of the proposed approach in optimizing multiple response problems.

References
[1] Montgomery DC. Design and analysis of experiments. 3rd edition. Wiley, New York. 1991.

[2] Carlos A, Coello Coello. An updated survey of GA-based multiobjective optimization techniques. ACM Computing Surveys. 2000; 32: 109-143.

[3] Hartmann N E, Beaumont R A. Optimum compounding by computer. Journal of the Institute of the Rubber Industry. 1968; 2: 272-275.

[4] Biles W E, Swain J J. Optimization and Industrial Experimentation. Wiley-Interscience, New York, USA. 1980.

[5] Box G E P, Liu P Y T. Empirical Model-Building and Response Surfaces. John Wiley & sons, New York, USA. 1987.

[6] Ortiz F, Simpson J, Pignatiello J, Heredia-Langner A. A Genetic Algorithm Approach to Multiple-Response Optimization. Journal of Quality Technology. 2004; 36: 432-450.

[7] Clayton E, Weber W, Taylor B W. A goal programming approach to the optimization of multi-response simulation models. IIE Transactions. 1982; 14: 282-287.

[8] Baesler FF, Sepulveda J A. Multi-response simulation optimization using stochastic genetic search within a goal-programming framework. proceedings of the 2000 Winter Simulation Conference. 2000.

[9] Myers R, Carter W. Response surface techniques for dual response systems. Technometrics. 1973; Vol.15: 301-317.

[10] Derringer G, Suich R. Simultaneous optimization of several response variables. Journal of Quality Technology. 1980; 12: 214-219.

[11] Pignatiello JJ. Strategies for robust multiresponse quality engineering. IIE Transactions. 1993; 25: 5-15.

[12] Derringer G. A balancing act: optimizing a product’s properties. Quality Progress. 1994; 27: 51-57.

[13] Kim K, Lin D. Dual response surface optimization: a fuzzy modeling approach. Journal of Quality Technology. 1998; Vol. 30: PP. 1-10.

[14] Kim K, Lin D. Optimization of multiple responses considering both location and dispersion effects. Working paper, POSTECH. 2002.

[15] Mollaghasemi M, Evans G, Biles W. An approach for optimizing multiple response simulation models. In Proceedings of the 13th Annual Conference on Computers in Industrial Engineering.1991: pp 201-203.

[16] Boyle CR. An interactive multiple response simulation optimization method. IIE Transactions.1996; 14:453-463.

[17] Myers R, Montgomery DC. Response Surface Methodology: Process and Product Optimization Using Designed Experiments. 2nd ed. John Wiley & Sons Inc.,New York. 2002.

[18] Su Y, Bao Z, Wang F, Watanabe T. Efficient GA Approach Combined with Taguchi Method for Mixed Constrained Circuit Design. International Conference on Computational Science and Its Applications (ICCSA). 2011: 290-293.

[19] Lo Y L, Tsao C C. Integrated Taguchi method and neural network analysis of physical profiling in the wirebonding process. IEEE Transactions on Components and Packaging Technologies. 2002; Vol.25. No. 2: P.P. 270-277.

[20] Noorossana R, et al. An artificial neural network approach for multiple-response optimization. The International Journal of Advanced Manufacturing Technology. 2009; vol. 40, no. 11: pp. 1227-1238.

[21] Akhoondinasab M, Shafaei Y, Rahmani A, Keshavarz H. A Machine Learning-Based Model for Breast Volume Prediction Using Preoperative Anthropometric Measurements. Aesthetic Plastic Surgery. 2024 Feb;48(3):243-9.

[22] Mahmoudiandehkordi S, Yeganegi M, Shomalzadeh M, Ghasemi Y, Kalatehjari M. Enhancing IVF Success: Deep Learning for Accurate Day 3 and Day 5 Embryo Detection from Microscopic Images. International Journal of Applied Data Science in Engineering and Health. 2024 Aug 14;1(1):18-25.

[23] Maydanchi M, Ziaei M, Mohammadi M, Ziaei A, Basiri M, Haji F, Gharibi K. A Comparative Analysis of the Machine Learning Methods for Predicting Diabetes. Journal of Operations Intelligence. 2024 May 18;2(1):230-51.

[24] Ashrafi N, Liu Y, Xu X, Wang Y, Zhao Z, Pishgar M. Deep learning model utilization for mortality prediction in mechanically ventilated ICU patients. Informatics in Medicine Unlocked. 2024 Jan 1;49:101562.

[25] Tashakkori A, Talebzadeh M, Salboukh F, Deshmukh L. Forecasting Gold Prices with MLP Neural Networks: A Machine Learning Approach. International Journal of Science and Engineering Applications (IJSEA). 2024; 13:13-20.

[26] Tashakkori A, Erfanibehrouz N, Mirshekari S, Sodagartojgi A, Gupta V. Enhancing stock market prediction accuracy with recurrent deep learning models: A case study on the CAC40 index. World Journal of Advanced Research and Reviews. 2024;23(1):2309-21.

[27] Mahdavimanshadi M, Fan N. Multistage Stochastic Optimization for Semi-arid Farm Crop Rotation and Water Irrigation Scheduling Under Drought Scenarios. Journal of Agricultural, Biological and Environmental Statistics. 2024 Sep 5:1-24.

[28] Zadeh SS, Khorshidi M, Kooban F. Concrete Surface Crack Detection with Convolutional-based Deep Learning Models. arXiv preprint arXiv:2401.07124. 2024 Jan 13.

[29] Zarreh M, Khandan M, Goli A, Aazami A, Kummer S. Integrating Perishables into Closed-Loop Supply Chains: A Comprehensive Review. Sustainability. 2024 Aug 5;16(15):6705.

[30] Khameneh RT. Metaheuristic approaches for maximum blood collection problem (Doctoral dissertation, Ozyegin University).

[31] Khameneh RT, Elyasi M, Özener OÖ, Ekici A. A non-clustered approach to platelet collection routing problem. Computers & Operations Research. 2023 Dec 1;160:106366.

[32] Karkehabadi A, Homayoun H, Sasan A. FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropogation. InProceedings of the Great Lakes Symposium on VLSI 2024 2024 Jun 12 (pp. 626-632).

[33] Aghakhani S, Pourmand P, Zarreh M. A Mathematical Optimization Model for the Pharmaceutical Waste Location‐Routing Problem Using Genetic Algorithm and Particle Swarm Optimization. Mathematical Problems in Engineering. 2023;2023(1):6165495.

[34] Subrarnanyam V, Srinivasan D, Oniganti R. Dual layered PSO Algorithm for evolving an Artificial Neural Network controller. IEEE/CEC. 2007: 2350-2357.

[35] Dou Q, Zhou C, Pan G, Luo H, Liu Q., Neural Particle Swarm Optimization for Casing Damage Prediction. Lecture Notes in Computer Science (LNCS). 2005; 3498:903-907.

[36] Chen C, Feng H, Ye F. Hybrid Recursive Particle Swarm Optimization Learning algorithm in the Design of Radial Basis Function Networks, J. of Marine Science and Technology.2007; Vol 15, No 1: 31-40.

[37] Madar J, Abonyi J, Szeifert F. Interactive particle swarm optimization. Proc. Int. IEEE conference on Intelligent Systems Design and Applications (IEEE/ ISDA). 2005; Vol.8, No.10: pp. 314–319.

[38] Lu H, Chen W. Self-adaptive velocity particle swarm optimization for solving constrained optimization problems. Journal of Global Optimization. 2008; Vol.41, No.3: pp. 427-445.

[39] Shen X, Wei K, Wu D, Tong Y, Li Y. A Dynamic Adaptive Dissipative Particle Swarm Optimization with Mutation Operation, Proc. IEEE/ ICCA. 2007: 586-589.

[40] Del Castillo E, Montgomery DC, McCarville DR. Modified desirability functions for multiple response optimization. Journal of Quality Technology. 1996; 3. 28: 337-345.

[41] Siljic Tomic A, Antanasijevic D, Ristic M, et al. Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction. Environ Sci Pollut Res. 2018; 25:9360–9370.

[42] Tong LI, Wang CH, Chen HC. Optimization of multiple responses using principal component analysis and technique for order preference by similarity to ideal solution. Int J Adv Manuf Technol.2005; 27, 407–414

[43] Tong LI, Chen CC, Wang CH. Optimization of multi-response processes using the VIKOR method. International Journal of Advanced Manufacturing Technology. 2007 Feb 1;31(11-12):1049-1057. doi: 10.1007/s00170-005-0284-6

[44] Orouskhani M, Daming S, Orouskhani Y. Multi-objective evolutionary clustering with complex networks. Expert Systems with Applications. 2021;165: 113916.

[45] Lin J L, Wang K S, Yan B H, Tarng Y S. Optimization of the electrical discharge machining process based on the Taguchi method with fuzzy logics. Journal of Materials Processing Technology. 2000; Vol. 102, no. 1: pp. 48–55.